跳到正文Skip to content
Agent J Beta
菜单Menu
中文EN
登录Sign in

搜索文档和页面Search docs and pages

文档Docs

离开电脑前，先把这些事一次做好Before you leave your computer

装好以后，趁你还在电脑前，让 Agent 把以后用手机远程工作要你本人帮忙的事一次列全、做完、验证。After installing, while you are still at the computer, let your Agent list, finish and verify everything remote work will need from you.

Agent J 装好、电脑浏览器和手机都配好以后，先别急着离开电脑。让你的 Agent 把以后用手机工作需要你本人协助的事一次检查好。你只需处理登录、系统提示和接电源这些必须本人做的事，其余交给它。

第一次安装时，Agent 会在新手引导结束后主动提议一次；已经在用的电脑不会自动弹出，需要时直接对 Agent 说就行。

把这句话发给你的 Agent：

我现在在电脑前。请把以后远程工作需要我本人协助的事情一次列全，先检查已经配置好的。我不用的可以跳过，其余按顺序带我做完并验证。密码和密钥只用手机专用卡，不进聊天。最后告诉我哪些事可以离开电脑继续做，还有哪些需要回来。

清单页

Agent 开始后，手机和电脑网页的聊天上方会出现一条细横幅：「首次准备 3/12 · 继续」。它不会挡住聊天，你随时都能继续跟 Agent 说话。点它打开独立的清单页，左上角箭头回到聊天。横幅右边的 ✕（或清单页上的「✕ 收起清单」）立即收起。在这台设备上它就一直关着：清单有新进度、复查、Agent 继续准备，甚至重启服务，都不会再把它弹回来。只有你自己能重新打开：在菜单里点「首次准备清单」，或者让 Agent 打开。也可以直接让 Agent 帮你关掉。

清单页顶部始终写着：这些步骤在电脑上做；手机上看进度；卡住了直接在聊天里告诉 Agent。清单分六组：基本连接、电源与服务、常用网站、Google 工具、按需系统权限、可选通道。每一项都标明「在电脑上做」「在手机上点」「我来做」或「本版还不支持」。

清单页每次突出一个当前事项，下面是完整清单：

  • 要用：这件事你要用，Agent 带你做完。
  • 我不用：只对可选项出现。Agent 会记住，直到你以后想用或某个新任务确实需要它。
  • 稍后：保留为没做完，不等于「我不用」。
  • 检查：让电脑重新检查一次。你说做完了，只会触发检查，检查通过才算完成。

必需的事项（账号、AI 登录、两个遥控器、通行密钥、后台服务、接电源不睡眠、网络、最后的手机检查）没有「我不用」。随时对 Agent 说「继续首次准备」，从上次停下的地方接着做，不用重装或重新配对。

某一项没通过时，清单页会直接写明查到了什么、影响什么、下一步点哪里，比如写明是 Agent J 的专用浏览器里还没登录 Gmail（你平时用的浏览器不算），只影响要用 Gmail 的事。只有依赖它的事会等，其他照常，Agent 也照常聊天。

先完成基本连接

登录你选用的一个 AI 工具，配好这台电脑的浏览器和主力手机，从手机发一条消息并收到回复。手机的通行密钥用于批准和支持的恢复；它不是电脑的管理员密码，也不能代替 Mac 的本机 Touch ID。

在香港、澳门、中国大陆等用不了 Claude Code 和 Codex 的地区，清单的「主 AI 登录与权限」一项按地区推荐：中国大陆从零开始首推火山方舟 Coding Plan，先买 Lite（和 Pro 能力一样，只差 5 倍用量）；香港 / 海外推荐 Kimi 会员 Plus 或更高档（通过 OpenCode，Go 档没有编程额度），并给出 Agent J 官方的邀请链接，链接后面紧跟「这是 Agent J 官方的邀请链接，您和我们各得一次抽奖」；已经有其中一家的就继续用。判断依据是实测，见装好 AI 命令行工具。

让电脑保持在线

插上电源，让电脑不睡眠；屏幕可以关闭，笔记本优先保持打开。Agent 会检查设置并保存可恢复的原值，改系统设置会发一张手机密码卡（见电脑防休眠）。Windows/WSL 要检查 Windows 本身，不能只改 WSL。Mac 若还要求本机 Touch ID，Agent 会说明需要你在电脑上处理哪一步，不会连续索要手机密码。

网站与 Google

常用网站（Gmail、YouTube Studio、B站、抖音、公众号等）要在电脑的正式登录页上由你本人登录。清单只读取 Agent J 所用浏览器的真实登录检查结果，从不读你平时用的浏览器，每个网站项都写明查的是哪个浏览器。超过 15 分钟的结果需要重新检查，光说做完了不能直接让网站通过。公众号和视频号分别检查，两项都通过才算完成微信这一项。

  • 在电脑上安装专用浏览器：Agent J 还没有浏览器时出现。
  • 用我已有的浏览器：你电脑上已经开着一个能被自动化工具连接的浏览器（比如端口 9222 上、各网站都已登录的 Chromium）时出现。Agent J 原样使用它：不另装一套，不启动、不关闭、不修改它，也不读取它的 cookie。之后网站组会显示「用的是：你已有的浏览器（端口 9222）」。
  • 在电脑上打开并登录：在 Agent J 的浏览器里打开登录页，并把窗口弹到最前面（Linux 的 Hyprland 或 X11、macOS 支持；其他环境清单页会提示你找标题为「Agent J 专用浏览器」的窗口）。Agent J 自己的浏览器和你平时的浏览器一眼就能分开：窗口标题写着「Agent J 专用浏览器 · Agent J browser」，起始页是紫色的。

Gmail 网页登录和 Google 的邮件、日历、云盘、YouTube 接口授权是两回事。这一版会预装 Google 工具，接口授权的一键引导在 0.18.1，详见 连接 Google。

只给需要的权限

普通对话、文件项目和浏览器操作不会一律要求 Mac 的辅助功能、完全磁盘访问和屏幕录制。只有你选的任务确实需要时，Agent 才说明是哪个程序、为什么要申请。手机语音、相机权限在手机上就能补，不必回电脑。

离开前做一次手机检查

其他已选事项都通过后，在卡片上点「开始离机检查」：让电脑屏幕熄灭，手机关掉 Wi-Fi 用蜂窝网络，在聊天里随便发一句话，收到回复就完成。

通过后你会看到：「从现在起，你可以离开电脑，用手机继续处理已选并验证的事项。」同时列出没启用的事项和检查时间。还有没做完的，只会告诉你手机对话已经能用、离机检查还剩几项，不会说所有事都能远程。

电脑断电、重启后要解锁、新的系统权限或账号安全检查，仍可能需要你回到电脑。付款、发信等操作仍会在手机上按具体事项请你批准；首次准备不会预先批准这些事，也不会为了省一次回来而关掉电脑的安全设置。

技术细节
  • 命令：agentj setup checklist --json（只读，没开始时返回 needs_setup）、agentj setup checklist --resume（开始或继续，手机和电脑网页出现横幅）、agentj setup checklist --check / --item <项>（复查；网站项会真去做一次只读登录检查）、agentj setup checklist --close（各处立即收起，之后不会自己弹回来）、agentj setup checklist --open（你要看时才重新打开）。没有任何命令能替你标记「我不用」或标记完成。
  • 用你已有的浏览器：agentj browser adopt --endpoint http://127.0.0.1:<端口> 只是提议（只限本机回环地址，其他一律拒绝），你在清单页点「用我已有的浏览器」才生效；--dry-run [--site gmail] 只读、不登记；agentj browser adopt --forget 不再使用它。agentj browser setup 发现已有浏览器会先问；加 --own 则照样安装专用浏览器。
  • 状态保存在本机状态目录的 setup/checklist.json（只有你自己的用户能读写），不上传云端。卡片上的选择由已配对设备签名，旧版本的卡片会被拒绝并刷新。
  • 检查有效期：网站 15 分钟，其他 24 小时；离机检查的手机回合 2 小时内有效。

Once Agent J is installed and this computer's browser and your phone are paired, stay at the computer for one final preparation round. Your Agent handles the technical work. You handle the sign-ins, system prompts and physical steps that need you.

After the first installation your Agent offers this once, when the welcome tour ends. Computers already in use never get it automatically; ask your Agent whenever you want it.

Send this to your Agent:

I am at my computer now. List everything that needs my help before I can work remotely, and check what is already configured. Let me decline things I will not use. Guide me through the rest in order and verify each result. Use secure phone cards for passwords and keys, never chat. Finish by telling me what I can do away from the computer and what might still require a return.

The checklist page

When your Agent starts, a thin bar appears above the chat on your phone and in this computer's browser: "First-run setup 3/12 · Continue". It never covers the chat, so you can always keep talking to your Agent. Tap it to open the checklist as its own page; the arrow takes you back to the chat. The bar's ✕ (or "✕ Close checklist" on the page) closes it at once. On that device it then stays closed for good: new progress, re-checks, your Agent continuing the setup, even a restart never bring it back. Only you open it again, from the menu under "First-run checklist" or by asking your Agent to show it. You can also ask your Agent to close it.

The top of the page always says: do these steps on the computer; watch progress on the phone; stuck? just tell your Agent in the chat. It has six groups: your connection, power and services, your websites, Google tools, permissions you need, and optional connections. Each item is labelled "On the computer", "Tap on the phone", "I do it" or "Not in this version".

The page shows one current item at a time, with the whole list below it:

  • Use it: you need it; your Agent guides you through it.
  • I won't use this: optional items only. Your Agent remembers until you ask for it or a new task truly needs it.
  • Later: kept as unfinished, which is not the same as "I won't use this".
  • Check: the computer checks again. Saying you are done only starts a check; the item completes when the check passes.

Required items (account, AI login, both remotes, passkey, background service, plugged in without sleep, network, the final phone check) have no "I won't use this". Say "Continue first-run setup" at any time to pick up where you stopped, without reinstalling or pairing again.

When an item has not passed, the page says exactly what was found, what it affects, and what to tap next — for example that Gmail is not signed in in Agent J's own browser (your everyday browser does not count) and only tasks that use Gmail wait. Only what depends on it waits; everything else continues, and your Agent keeps chatting.

Connect first

Sign in to one AI tool. Pair this computer's browser and your main phone, then send a message from the phone and receive a reply. A phone passkey approves supported requests and recovery. It is separate from the computer's administrator password and a Mac's local Touch ID prompt.

Where Claude Code and Codex are not offered (Hong Kong, Macau, mainland China and similar), the checklist's "Main AI login and access" row recommends by region: in mainland China, starting from zero, Volcano Ark Coding Plan — buy Lite first (same as Pro, only 1/5 of the quota); in Hong Kong / overseas, a Kimi membership, Plus or higher, through OpenCode (the Go plan has no coding quota), with Agent J's official invite link and this sentence right next to it: "This is Agent J's official invite link: you and we each get one prize draw". Already paying for one of them? Keep it. The decision comes from a real check; see Set up AI command-line tools.

Keep the computer reachable

Plug it in and keep the laptop open. The display may turn off while the computer keeps working. Your Agent checks the settings and keeps the original values; a system change comes to your phone as a password card (see Keep the computer awake). With Windows and WSL, Windows itself needs checking. If a Mac still asks for local Touch ID, your Agent explains the local step instead of asking for the phone password again and again.

Websites and Google

Sign in to your websites (Gmail, YouTube Studio and others) yourself, on the real sign-in page on the computer. The checklist reads the sign-in checks of the browser Agent J uses, never your everyday browser, and every website row says which browser it checked. A check older than 15 minutes needs refreshing; saying you are done cannot make a site pass. WeChat completes only when both Official Accounts and Channels pass their own checks.

  • Install Agent J's browser on the computer: when Agent J has no browser yet.
  • Use my existing browser: when you already run a browser that automation tools connect to on this computer (for example a Chromium on port 9222, already signed in everywhere). Agent J uses it as it is: it never installs a second one, never starts, stops or changes it, and never reads its cookies. The browser group then shows "Using: your own browser (port 9222)".
  • Open it on the computer and sign in: the sign-in page opens in Agent J's browser and its window comes to the front (Linux with Hyprland or X11, and macOS; elsewhere the page tells you to find the window titled "Agent J browser"). Agent J's own window is easy to tell apart from your everyday browser: its title says "Agent J 专用浏览器 · Agent J browser" and its start page is purple.

Signing in to Gmail's website is not the same as authorizing Gmail, Calendar, Drive or YouTube tools. This version pre-installs the Google tools; guided authorization arrives in 0.18.1. See Connect Google.

Grant only the permissions you need

Chat, file work and browser automation do not automatically require every Mac privacy permission. Only when a task you chose needs one does your Agent name the program and the reason. Phone microphone and camera permissions can be granted on the phone later.

Check before you leave

When everything else you chose has passed, tap "Start the leaving check" on the card: let the computer's display turn off, switch the phone to mobile data, and send any chat message. A reply completes it.

You then see "You can now leave your computer and continue the selected, verified tasks from your phone." It also lists the items you did not enable and the check time. If anything is unfinished, you see what already works and how many items are left, never a claim that everything is remote.

Power loss, a restart that needs unlocking, a new system permission or an account security check may still need you at the computer. Sending, paying and similar actions still ask for their own approval on the phone; the first-run checklist does not approve them in advance, and it never turns off a security setting to save you a trip.

Technical details
  • Commands: agentj setup checklist --json (read-only; needs_setup before you start), agentj setup checklist --resume (start or continue and show the banner on the phone and this computer's browser), agentj setup checklist --check / --item <id> (re-check; a website item runs a real read-only sign-in check), agentj setup checklist --close (close it everywhere at once; nothing reopens it by itself), agentj setup checklist --open (show it again, only when you ask). No command can mark "I won't use this" or "done" for you.
  • Your existing browser: agentj browser adopt --endpoint http://127.0.0.1:<port> only proposes it (this computer's loopback only; anything else is refused) — it takes effect when you tap "Use my existing browser"; --dry-run [--site gmail] only reads and registers nothing; agentj browser adopt --forget stops using it. agentj browser setup asks first when it finds one; --own installs Agent J's browser anyway.
  • The state lives in setup/checklist.json in the local state folder (readable only by your user) and is not uploaded. Choices on the card are signed by a paired device; a card showing an older revision is refused and refreshed.
  • Freshness: websites 15 minutes, everything else 24 hours; the leaving check's phone round trip counts for 2 hours.

这一页的 Markdown 原文This page as Markdown: zh.md · en.md